Motion-Aware Caching for Efficient Autoregressive Video Generation

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of $\textbf{6.28}\times$ and $\textbf{1.64}\times$ respectively, while effectively preserving generation quality (VBench: $1\%\downarrow$ and $0.01\%\downarrow$ respectively). The code is available at https://github.com/ywlq/MotionCache.

Prototype-Based Test-Time Adaptation of Vision-Language Models

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on cache-based designs, but these introduce two key limitations. First, inference latency increases as the cache grows with the number of classes, leading to inefficiencies in large-scale settings. Second, suboptimal performance occurs when the cache contains insufficient or incorrect samples. In this paper, we present Prototype-Based Test-Time Adaptation (PTA), an efficient and effective TTA paradigm that uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples. Particularly, knowledge prototypes are adaptively weighted based on the zero-shot class confidence of each test sample, incorporating the sample's visual features into the corresponding class-specific prototype. It is worth highlighting that the knowledge from past test samples is integrated and utilized solely in the prototypes, eliminating the overhead of cache population and retrieval that hinders the efficiency of existing TTA methods. This endows PTA with extremely high efficiency while achieving state-of-the-art performance on 15 image recognition benchmarks and 4 robust point cloud analysis benchmarks. For example, PTA improves CLIP's accuracy from 65.64% to 69.38% on 10 cross-domain benchmarks, while retaining 92% of CLIP's inference speed on large-scale ImageNet-1K. In contrast, the cache-based TDA achieves a lower accuracy of 67.97% and operates at only 50% of CLIP's inference speed.

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference

Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token importance and diversity: importance-based methods tend to retain redundant tokens, whereas diversity-based methods may overlook informative ones. This trade-off becomes especially problematic under high reduction ratios, where preserving only a small subset of visual tokens is critical. To address this issue, we propose ID-Selection, a simple yet effective token selection strategy for efficient LVLM inference. The key idea is to couple importance estimation with diversity-aware iterative selection: each token is first assigned an importance score, after which high-scoring tokens are selected one by one while the scores of similar tokens are progressively suppressed. In this way, ID-Selection preserves informative tokens while reducing redundancy in a unified selection process. Extensive experiments across 5 LVLM backbones and 16 main benchmarks demonstrate that ID-Selection consistently achieves superior performance and efficiency, especially under extreme pruning ratios. For example, on LLaVA-1.5-7B, ID-Selection prunes 97.2% of visual tokens, retaining only 16 tokens, while reducing inference FLOPs by over 97% and preserving 91.8% of the original performance, all without additional training.

Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism

Long video understanding is a key challenge that plagues the advancement of \emph{Multimodal Large language Models} (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed \emph{Flexible Memory} (\textbf{FlexMem}). In principle, FlexMem aims to mimic human behavior of video watching, \emph{i.e.}, continually watching video content and recalling the most relevant memory fragments to answer the question. In this way, FlexMem can help MLLMs achieve video understanding of infinite lengths, unlike previous methods that process all video information at once and have input upper-limit. Concretely, FlexMem first consider the visual KV caches as the memory sources, and realize the effective memory transfer and writing via a dual-pathway compression design. Afterwards, FlexMem also explores different memory reading strategies for the diverse video understanding tasks, including the popular streaming one. To validate FlexMem, we apply it to two popular video-MLLMs, and conduct extensive experiments on five long video and one streaming video task. The experimental results show that on \textbf{a single 3090 GPU}, our FlexMem can achieve obvious improvements than existing efficient video understanding methods and process more than \textbf{1k frames}, which also helps the base MLLMs achieve comparable or even better performance than SOTA MLLMs on some benchmarks, \emph{e.g.} , GPT-4o and Gemini-1.5 Pro.

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead. This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level concurrency. To this end, we propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck. Our key insight is that a lightweight, tool-free MLLM can serve as a speculative planner to predict the execution trajectory, enabling early termination of expensive tool chains without sacrificing accuracy. To regulate this speculative planning, we introduce a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels. Furthermore, we design a heterogeneous parallel funnel that exploits the stateless concurrency of the small model to mask the stateful serial execution of the large model, maximizing system throughput. Extensive experiments on V* Bench, HR-Bench, and POPE demonstrate that SpecEyes achieves 1.1-3.35x speedup over the agentic baseline while preserving or even improving accuracy (up to +6.7%), thereby boosting serving throughput under concurrent workloads.

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of high-ratio token compression. We attribute this shortcoming to the insufficient modeling of temporal and continual video content, and propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune, which achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling. In practice, ForestPrune construct token forests across video frames based on the semantic, spatial and temporal constraints, making an overall comprehension of videos. Afterwards, ForestPrune evaluates the importance of token trees and nodes based on tree depth and node roles, thereby obtaining a globally optimal pruning decision. To validate ForestPrune, we apply it to two representative video MLLMs, namely LLaVA-Video and LLaVA-OneVision, and conduct extensive experiments on a bunch of video benchmarks. The experimental results not only show the great effectiveness for video MLLMs, e.g., retaining 95.8% average accuracy while reducing 90% tokens for LLaVA-OneVision, but also show its superior performance and efficiency than the compared token compression methods, e.g., +10.1% accuracy on MLVU and -81.4% pruning time than FrameFusion on LLaVA-Video.

Persistent Story World Simulation with Continuous Character Customization

Story visualization has gained increasing attention in computer vision. However, current methods often fail to achieve a synergy between accurate character customization, semantic alignment, and continuous integration of new identities. To tackle this challenge, in this paper we present EverTale, a story world simulator for continuous story character customization. We first propose an All-in-One-World Character Integrator to achieve continuous character adaptation within unified LoRA module, eliminating the need for per-character optimization modules of previous methods. Then, we incorporate a Character Quality Gate via MLLM-as-Judge to ensure the fidelity of each character adaptation process through chain-of-thought reasoning, determining whether the model can proceed to the next character or require additional training on the current one. We also introduce a Character-Aware Region-Focus Sampling strategy to address the identity degradation and layout conflicts in existing multi-character visual storytelling, ensuring natural multi-character generation by harmonizing local character-specific details with global scene context with higher efficiency. Experimental results show that our EverTale achieves superior performance against a wider range of compared methods on both single- and multi-character story visualization. Codes will be available.

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (when to interject), and (iii) natural interruption generation (how to phrase the interruption). SocialOmni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances with strict temporal and contextual constraints, complemented by controlled audio-visual inconsistency scenarios to test model robustness. We benchmarked 12 leading OLMs, which uncovers significant variance in their social-interaction capabilities across models. Furthermore, our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions, indicating that understanding-centric metrics alone are insufficient to characterize conversational social competence. More encouragingly, these diagnostics from SocialOmni yield actionable signals for bridging the perception-interaction divide in future OLMs.

Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and inefficient. To address this, we introduce a parameter- and data-efficient framework named Efficient Draft Adaptation, abbreviated as EDA, for efficiently adapting draft models. EDA introduces three innovations: (1) a decoupled architecture that utilizes shared and private components to model the shared and target-specific output distributions separately, enabling parameter-efficient adaptation by updating only the lightweight private component;(2) a data regeneration strategy that utilizes the fine-tuned target model to regenerate training data, thereby improving the alignment between training and speculative decoding, leading to higher average acceptance length;(3) a sample selection mechanism that prioritizes high-value data for efficient adaptation. Our experiments show that EDA effectively restores speculative performance on fine-tuned models, achieving superior average acceptance lengths with significantly reduced training costs compared to full retraining. Code is available at https://github.com/Lyn-Lucy/Efficient-Draft-Adaptation.

Event-Anchored Frame Selection for Effective Long-Video Understanding

Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approaches, however, adopt a flat sampling paradigm which treats the video as an unstructured collection of frames. In this paper, we introduce Event-Anchored Frame Selection (EFS), a hierarchical, event-aware pipeline. Leveraging self-supervised DINO embeddings, EFS first partitions the video stream into visually homogeneous temporal segments, which serve as proxies for semantic events. Within each event, it then selects the most query-relevant frame as an anchor. These anchors act as structural priors that guide a global refinement stage using an adaptive Maximal Marginal Relevance (MMR) scheme. This pipeline ensures the final keyframe set jointly optimizes for event coverage, query relevance, and visual diversity. As a training-free, plug-and-play module, EFS can be seamlessly integrated into off-the-shelf LVLMs, yielding substantial gains on challenging video understanding benchmarks. Specifically, when applied to LLaVA-Video-7B, EFS improves accuracy by 4.7%, 4.9%, and 8.8% on VideoMME, LongVideoBench, and MLVU, respectively.